A commercial recommendation prompt. We size how many people ask ChatGPT this from real search demand, then run it through ChatGPT to see which websites it recommends.
One of the 5 times we asked ChatGPT this, verbatim. The leaderboard below aggregates all 5 runs.
Aggregated across 5 runs (min 2/5 appearances). Estimated visits split the prompt's demand by rank. Sites matching the prompt's own brand are marked branded and excluded from the leaderboard.
| Rank | Website | Appears | Est. visits / mo | Est. value / mo |
|---|---|---|---|---|
| 1 | macrotrends.net | 4/5 | 2 | $0 |
| 2 | investopedia.com | 3/5 | 1 | $0 |
| 3 | tradingview.com | 3/5 | 1 | $0 |
| 4 | bloomberg.com | 3/5 | 1 | $0 |
| 5 | marketwatch.com | 3/5 | 0 | $0 |
| 6 | cnbc.com | 3/5 | 0 | $0 |
| 7 | reuters.com | 3/5 | 0 | $0 |
| 8 | flickr.com | 2/5 | 0 | $0 |
| 9 | babypips.com | 2/5 | 0 | $0 |
| 11 | wsj.com | 3/5 | 0 | $0 |
| 12 | forexfactory.com | 2/5 | 0 | $0 |
| 13 | fxstreet.com | 2/5 | 0 | $0 |
| 14 | macromicro.me | 2/5 | 0 | $0 |
| 15 | ft.com | 3/5 | 0 | $0 |
| 16 | 500px.com | 2/5 | 0 | $0 |
| 17 | youtube.com | 2/5 | 0 | $0 |
| 18 | thebalance.com | 2/5 | 0 | $0 |
| 19 | economist.com | 2/5 | 0 | $0 |
| 20 | imf.org | 3/5 | 0 | $0 |
ChatGPT doesn't publish prompts, so we don't show logged conversations. We measure real demand for this topic from Google search volume, scale it to ChatGPT's user base (on average about 1 ChatGPT user for every 8 Google searchers, a ratio that varies by topic), and run the prompt through ChatGPT 5 times to record which websites it recommends and in what order. Estimated visits split that demand across the recommended sites by a click-through-by-rank curve. Every number is a modeled estimate, not measured analytics. Full methodology →